https://github.com/xuyxu/deep-clustering-network
PyTorch Implementation of "Towards K-Means-Friendly Spaces: Simultaneous Deep Learning and Clustering," Bo Yang et al., ICML'2017.
https://github.com/xuyxu/deep-clustering-network
clustering deep-learning pytorch
Last synced: about 1 year ago
JSON representation
PyTorch Implementation of "Towards K-Means-Friendly Spaces: Simultaneous Deep Learning and Clustering," Bo Yang et al., ICML'2017.
- Host: GitHub
- URL: https://github.com/xuyxu/deep-clustering-network
- Owner: xuyxu
- Created: 2020-08-29T01:37:26.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2021-01-15T12:37:49.000Z (over 5 years ago)
- Last Synced: 2025-04-14T11:07:10.772Z (about 1 year ago)
- Topics: clustering, deep-learning, pytorch
- Language: Python
- Homepage:
- Size: 109 KB
- Stars: 128
- Watchers: 3
- Forks: 31
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
### DCN: Deep Clustering Network
I found the official implementation of deep clustering network (DCN) is outdated (https://github.com/boyangumn/DCN-New). This repo is a re-implementation of DCN using PyTorch.
#### Introduction
An interesting work that jointly performs unsupervised dimension reduction and clustering using a neural network autoencoder.
#### How to run
Here I offer a demo on training DCN on the MNIST dataset (corresponding to Section 5.2.5 in the raw paper). To run this demo, simply type the following command:
```
python mnist.py
```
#### Acknowledgement
For anyone with interests, you can also refer to the implementation of Günther Eder: https://github.com/guenthereder/Deep-Clustering-Network, which has more details on the reproducibility.
#### Experiment
I trained the DCN model on MNIST dataset, hyper-parameters like network structure were set as values reported in the paper. The left figure presents the reconstruction error of the autoencoder during the pre-training stage, and the right figure presents changes on NMI and ARI (two metrics employed in the paper) during the training stage. The best NMI result I have got is around 0.65.
#### Package dependency
* scikit-lean==0.23.1
* pytorch==1.6.0
* torchvision==0.7.0
* joblib==0.16.0
In my practice, this implementation also works fine on PyTorch 0.4.1. Feel free to open an issue if there were incompatibility problems.
#### Reference
* Yang et al. ''Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering'', ICML-2017 (https://arxiv.org/pdf/1610.04794.pdf)